一种低信噪比条件下的红外图像序列小目标实时检测算法

本文提出了一种基于多级门限判决与轨迹置信度检验的弱小目标检测方法,该方法综合利用能量积累、多级门限判决与轨迹搜索方法,同时对候选多目标轨迹进行置信度检验,剔除假目标,给出真目标信息。该算法针对高空背景条件下的图像目标检测,以较小的运算量和存储空间开销,解决了低信噪比条件下的弱小运动目标的检测问题,算法简洁且易于进行软硬件分割实现,算法实时性能良好。文中最后给出其实验结果。

A Real-time Low SNR Small Target Detection Algorithm For IR Sequential Image

Low SNR moving small target detection is important in target detection, recognition and tracking system. In this paper, we put forward a new method of Low SNR moving small target detection based on multi-level threshold decision-making and sliding trajectory confidence test technology. The method completes the detection of small moving target in low SNR by synthesized energy accumulating, multi-level threshold decision-making, trajectory searching, and gliding confidence testing. The method has high detection probability and low false alarm probability, easy for software and hardware segment, simplicity and stabilization, and excellent real time performance. And experiments result is given in the paper.